Sonnet 5 is only good at one thing (beating Sonnet 4.6)
An article to dissect how much can you trust Anthropic's press release vs the community backlash.
Senior Data Science Lead
I write about Data Science, Machine Learning and leading data teams. I have built teams from scratch and lead 50+ data scientists @Skyscanner. Now, I share my experience with you.
Live Last read · last published · next check
Latest posts
Module 8 - How to balance dominant bar chart categories
Why default bars fail when one value explodes — and the only fix that actually works.
🚀 August on Sr Data Science Lead: What’s coming up.
3 articles - data viz, Sonnet 5 and Google TabFM.
Anthropic is telling you that Agentic Analytics is not just text-to-SQL
Anthropic's Agentic Analytics suite using Claude achieves 95% accuracy and they share how in their latest post. Trustworthy analytics is all about semantic layers, skills, evals, and data engineering.
Module 7 - Cropping the y-axis (when it helps… and when it lies)
A chapter in the Master Data Storytelling course on spotting when a y-axis hides the signal, exaggerates noise or needs a different chart entirely.
Understanding Transformers (Part 5): The final simple layers doing some heavy lifting
A guide to understand LayerNorm, residuals, feed-forward blocks, and the encoder-decoder pipe in the transformers architecture.
You don't need thinking levels in Claude Code. You need Planning and Goal modes.
Why Claude Code's most-hyped setting matters less than the discipline you apply before you prompt
🚀 July on Sr Data Science Lead: What’s coming up
4 articles - data viz, Transformers, Claude thinking levels and Agentic Analytics in Anthropic.
Claude Code agents: what they actually are
A ground-up guide to subagents In Claude Code for practitioners who want to understand the feature before building with it.
Understanding Transformers (Part 4): Attention is just a few matrices
How simple matrix operations unlock context, meaning, and the magic behind modern AI.